Examples with CloseShieldInputStream org.apache.commons.io.input.CloseShieldInputStream used on opensource projects

Example 6 with CloseShieldInputStream

use of org.apache.commons.io.input.CloseShieldInputStream in project lucene-solr by apache.

the class HttpSolrCall method remoteQuery.

private void remoteQuery(String coreUrl, HttpServletResponse resp) throws IOException {
    HttpRequestBase method = null;
    HttpEntity httpEntity = null;
    try {
        String urlstr = coreUrl + queryParams.toQueryString();
        boolean isPostOrPutRequest = "POST".equals(req.getMethod()) || "PUT".equals(req.getMethod());
        if ("GET".equals(req.getMethod())) {
            method = new HttpGet(urlstr);
        } else if ("HEAD".equals(req.getMethod())) {
            method = new HttpHead(urlstr);
        } else if (isPostOrPutRequest) {
            HttpEntityEnclosingRequestBase entityRequest = "POST".equals(req.getMethod()) ? new HttpPost(urlstr) : new HttpPut(urlstr);
            // Prevent close of container streams
            InputStream in = new CloseShieldInputStream(req.getInputStream());
            HttpEntity entity = new InputStreamEntity(in, req.getContentLength());
            entityRequest.setEntity(entity);
            method = entityRequest;
        } else if ("DELETE".equals(req.getMethod())) {
            method = new HttpDelete(urlstr);
        } else {
            throw new SolrException(SolrException.ErrorCode.SERVER_ERROR, "Unexpected method type: " + req.getMethod());
        }
        for (Enumeration<String> e = req.getHeaderNames(); e.hasMoreElements(); ) {
            String headerName = e.nextElement();
            if (!"host".equalsIgnoreCase(headerName) && !"authorization".equalsIgnoreCase(headerName) && !"accept".equalsIgnoreCase(headerName)) {
                method.addHeader(headerName, req.getHeader(headerName));
            }
        }
        // These headers not supported for HttpEntityEnclosingRequests
        if (method instanceof HttpEntityEnclosingRequest) {
            method.removeHeaders(TRANSFER_ENCODING_HEADER);
            method.removeHeaders(CONTENT_LENGTH_HEADER);
        }
        final HttpResponse response = solrDispatchFilter.httpClient.execute(method, HttpClientUtil.createNewHttpClientRequestContext());
        int httpStatus = response.getStatusLine().getStatusCode();
        httpEntity = response.getEntity();
        resp.setStatus(httpStatus);
        for (HeaderIterator responseHeaders = response.headerIterator(); responseHeaders.hasNext(); ) {
            Header header = responseHeaders.nextHeader();
            // encoding issues with Tomcat
            if (header != null && !header.getName().equalsIgnoreCase(TRANSFER_ENCODING_HEADER) && !header.getName().equalsIgnoreCase(CONNECTION_HEADER)) {
                resp.addHeader(header.getName(), header.getValue());
            }
        }
        if (httpEntity != null) {
            if (httpEntity.getContentEncoding() != null)
                resp.setCharacterEncoding(httpEntity.getContentEncoding().getValue());
            if (httpEntity.getContentType() != null)
                resp.setContentType(httpEntity.getContentType().getValue());
            InputStream is = httpEntity.getContent();
            OutputStream os = resp.getOutputStream();
            IOUtils.copyLarge(is, os);
        }
    } catch (IOException e) {
        sendError(new SolrException(SolrException.ErrorCode.SERVER_ERROR, "Error trying to proxy request for url: " + coreUrl, e));
    } finally {
        Utils.consumeFully(httpEntity);
    }
}

Example 7 with CloseShieldInputStream

use of org.apache.commons.io.input.CloseShieldInputStream in project tika by apache.

the class Word2006MLParser method parse.

@Override
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    //set OfficeParserConfig if the user hasn't specified one
    configure(context);
    final XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    try {
        context.getSAXParser().parse(new CloseShieldInputStream(stream), new OfflineContentHandler(new EmbeddedContentHandler(new Word2006MLDocHandler(xhtml, metadata, context))));
    } catch (SAXException e) {
        throw new TikaException("XML parse error", e);
    } finally {
        xhtml.endDocument();
    }
}

Example 8 with CloseShieldInputStream

use of org.apache.commons.io.input.CloseShieldInputStream in project tika by apache.

the class AbstractXML2003Parser method parse.

@Override
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    setContentType(metadata);
    final XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    TaggedContentHandler tagged = new TaggedContentHandler(xhtml);
    try {
        context.getSAXParser().parse(new CloseShieldInputStream(stream), new OfflineContentHandler(new EmbeddedContentHandler(getContentHandler(tagged, metadata, context))));
    } catch (SAXException e) {
        tagged.throwIfCauseOf(e);
        throw new TikaException("XML parse error", e);
    } finally {
        xhtml.endDocument();
    }
}

Example 9 with CloseShieldInputStream

use of org.apache.commons.io.input.CloseShieldInputStream in project tika by apache.

the class OOXMLExtractorFactory method parse.

public static void parse(InputStream stream, ContentHandler baseHandler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    Locale locale = context.get(Locale.class, Locale.getDefault());
    ExtractorFactory.setThreadPrefersEventExtractors(true);
    try {
        OOXMLExtractor extractor;
        OPCPackage pkg;
        // Locate or Open the OPCPackage for the file
        TikaInputStream tis = TikaInputStream.cast(stream);
        if (tis != null && tis.getOpenContainer() instanceof OPCPackage) {
            pkg = (OPCPackage) tis.getOpenContainer();
        } else if (tis != null && tis.hasFile()) {
            pkg = OPCPackage.open(tis.getFile().getPath(), PackageAccess.READ);
            tis.setOpenContainer(pkg);
        } else {
            InputStream shield = new CloseShieldInputStream(stream);
            pkg = OPCPackage.open(shield);
        }
        // Get the type, and ensure it's one we handle
        MediaType type = ZipContainerDetector.detectOfficeOpenXML(pkg);
        if (type == null || OOXMLParser.UNSUPPORTED_OOXML_TYPES.contains(type)) {
            // Not a supported type, delegate to Empty Parser
            EmptyParser.INSTANCE.parse(stream, baseHandler, metadata, context);
            return;
        }
        metadata.set(Metadata.CONTENT_TYPE, type.toString());
        // Have the appropriate OOXML text extractor picked
        POIXMLTextExtractor poiExtractor = null;
        // This has already been set by OOXMLParser's call to configure()
        // We can rely on this being non-null.
        OfficeParserConfig config = context.get(OfficeParserConfig.class);
        if (config.getUseSAXDocxExtractor()) {
            poiExtractor = trySXWPF(pkg);
        }
        if (poiExtractor == null && config.getUseSAXPptxExtractor()) {
            poiExtractor = trySXSLF(pkg);
        }
        if (poiExtractor == null) {
            poiExtractor = ExtractorFactory.createExtractor(pkg);
        }
        POIXMLDocument document = poiExtractor.getDocument();
        if (poiExtractor instanceof XSSFBEventBasedExcelExtractor) {
            extractor = new XSSFBExcelExtractorDecorator(context, poiExtractor, locale);
        } else if (poiExtractor instanceof XSSFEventBasedExcelExtractor) {
            extractor = new XSSFExcelExtractorDecorator(context, poiExtractor, locale);
        } else if (poiExtractor instanceof XWPFEventBasedWordExtractor) {
            extractor = new SXWPFWordExtractorDecorator(metadata, context, (XWPFEventBasedWordExtractor) poiExtractor);
            metadata.add("X-Parsed-By", XWPFEventBasedWordExtractor.class.getCanonicalName());
        } else if (poiExtractor instanceof XSLFEventBasedPowerPointExtractor) {
            extractor = new SXSLFPowerPointExtractorDecorator(metadata, context, (XSLFEventBasedPowerPointExtractor) poiExtractor);
            metadata.add("X-Parsed-By", XSLFEventBasedPowerPointExtractor.class.getCanonicalName());
        } else if (document == null) {
            throw new TikaException("Expecting UserModel based POI OOXML extractor with a document, but none found. " + "The extractor returned was a " + poiExtractor);
        } else if (document instanceof XMLSlideShow) {
            extractor = new XSLFPowerPointExtractorDecorator(context, (org.apache.poi.xslf.extractor.XSLFPowerPointExtractor) poiExtractor);
        } else if (document instanceof XWPFDocument) {
            extractor = new XWPFWordExtractorDecorator(context, (XWPFWordExtractor) poiExtractor);
        } else {
            extractor = new POIXMLTextExtractorDecorator(context, poiExtractor);
        }
        // Get the bulk of the metadata first, so that it's accessible during
        //  parsing if desired by the client (see TIKA-1109)
        extractor.getMetadataExtractor().extract(metadata);
        // Extract the text, along with any in-document metadata
        extractor.getXHTML(baseHandler, metadata, context);
    } catch (IllegalArgumentException e) {
        if (e.getMessage() != null && e.getMessage().startsWith("No supported documents found")) {
            throw new TikaException("TIKA-418: RuntimeException while getting content" + " for thmx and xps file types", e);
        } else {
            throw new TikaException("Error creating OOXML extractor", e);
        }
    } catch (InvalidFormatException e) {
        throw new TikaException("Error creating OOXML extractor", e);
    } catch (OpenXML4JException e) {
        throw new TikaException("Error creating OOXML extractor", e);
    } catch (XmlException e) {
        throw new TikaException("Error creating OOXML extractor", e);
    }
}

Example 10 with CloseShieldInputStream

use of org.apache.commons.io.input.CloseShieldInputStream in project tika by apache.

the class OpenDocumentContentParser method parseInternal.

void parseInternal(InputStream stream, final ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    DefaultHandler dh = new OpenDocumentElementMappingContentHandler(handler, MAPPINGS);
    SAXParser parser = context.getSAXParser();
    parser.parse(new CloseShieldInputStream(stream), new OfflineContentHandler(new NSNormalizerContentHandler(dh)));
}